© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88255
    Prev
    Next
    INDEX
    Explanations

    Technical/Informational content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éķĬ
    -0.27
    åħ¥åĽŃ
    -0.26
     enr
    -0.25
     telling
    -0.25
    ="'.
    -0.25
    odom
    -0.24
    çī¹éĤĢ
    -0.24
    åĨ·åį´
    -0.24
    /****************************************************************************
    -0.24
    ewood
    -0.24
    POSITIVE LOGITS
     Discussions
    0.25
    ISIS
    0.24
     Candidate
    0.24
    ListNode
    0.23
    æĨĭ
    0.23
    waters
    0.23
     Container
    0.23
    start
    0.23
    ury
    0.23
    demo
    0.23
    Activations Density 3.920%

    No Known Activations